AI Summary
5 min readWhat Claude Actually Did to the Riemann Hypothesis
In 30 hours, an unreleased version of Claude orchestrated a swarm of 60 autonomous subagents that ran 2,400 shell commands, executed hundreds of Python scripts, consumed 31 million output tokens, and autonomously downloaded 54 academic papers from arXiv. The result: it pushed the known lower bound on the proportion of non-trivial zeros of the Riemann zeta function lying on the critical line from 41.7% to 67.25%. The human who prompted it was not a mathematician. He was a software engineer named Jared Sumner who, according to Anthropic, was jogging when he opened a terminal on his phone and told the model to "believe in itself."
Why the Riemann Hypothesis Matters
The Riemann hypothesis is widely considered the most important unsolved problem in mathematics. To understand why, you have to start with the Basel problem, first posed in the 1600s: what is the sum of the infinite series 1 + 1/4 + 1/9 + 1/16 + ...? Euler solved it, showing the answer is π²/6. But he did something far more important in the process: he generalized the problem into what is now called the zeta function, and he proved that the sum over all natural numbers could be rewritten as a product over all primes. This is Euler's product formula, and it reveals a deep connection between the zeta function and the building blocks of arithmetic.
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of From First Principles
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (00:00) **Teaser: Claude and the Riemann Hypothesis** - The hosts introduce the strange story of Claude needing to be told to "believe in itself" before it tackled one of math's biggest problems.
- 2 (02:45) **Why the Riemann Hypothesis is the Holy Grail** - The hosts explain why this specific problem is the gold standard for judging AI's mathematical ability.
- 3 (09:33) **The Basel Problem and Euler's Genius** - The hosts begin building the mathematical foundation, starting with the problem that led to the creation of the Zeta function.
- 4 (13:34) **Euler's Product Formula: Connecting Sums and Primes** - The hosts break down Euler's key insight that links the Zeta function to the distribution of prime numbers.
- 5 (22:02) **Gauss, Riemann, and the Prime Number Theorem** - The hosts trace the history from Gauss's teenage prime-counting to Riemann's extension of the Zeta function into the complex plane.
- 6 (30:30) **Analytic Continuation and the "Sum" of Natural Numbers** - The hosts explain Riemann's crucial technique of extending the Zeta function to the entire complex plane.
- 7 (38:13) **The Hypothesis: Zeros on the Critical Line** - The hosts finally state the Riemann Hypothesis and explain its profound implications for understanding prime numbers.
+ Full timestamped outline available in the app
Show Notes
Claude did not solve the Riemann Hypothesis. But what it actually did may be one of the clearest examples yet of how rapidly AI systems are changing the way difficult mathematics can be attacked.
In Episode 53, Lester Nare and Krishna Choudhary go from first principles on arguably the most famous unsolved problem in mathematics.
We begin with Euler and the Basel problem, build the Riemann zeta function from the ground up, explain its deep connection to prime numbers, move into the complex plane and analytic continuation, unpack the famous 1 + 2 + 3 + 4 + … = -1/12 result, and finally arrive at the Riemann Hypothesis itself: the claim that every non-trivial zero of the zeta function lies on the critical line.
Then we get into Claude.
An unreleased Anthropic model was prompted to take a serious run at the problem. It orchestrated roughly 60 autonomous sub-agents, tested hundreds of mathematical approaches, executed code, searched academic literature, challenged its own strategies, created adversarial referees to attack its work, and ultimately produced a result pushing a related mathematical bound well beyond the previous state of the art.
The human behind the prompt was not a mathematician. One of his instructions was essentially: believe in yourself.
We explain what Claude actually accomplished, what it absolutely did not accomplish, why moving a bound toward two-thirds does not mean the Riemann Hypothesis is “two-thirds solved,” and what the process tells us about agentic AI, mathematical research, scientific discovery, and AI safety.
Then it’s transfer season.
For the first FFP Summer Transfer Window for Scientists, we look at prominent researchers leaving American institutions for universities and research centers abroad. Using the language of football transfers, we examine major moves in chemistry, battery research, gravitational-wave astrophysics, and neuroscience—and what they reveal about research funding, immigration, scientific infrastructure, and the global competition for talent.
Explore the FFP science funding tracker:ffppod.com/funding
Help shape Year Two and enter the anniversary merch giveaway:ffppod.com/survey
Support the show:ffppod.com/donate
Follow:@FFPPod on X / Instagram / TikTok / Facebook
More from this podcast
From First Principles →